A method and system for predicting equipment defects

Abstract

The present invention belongs to the field of equipment management, and in particular, relates to a method and system for predicting equipment defects, the method comprising: collecting defect data of abnormal equipment and analyzing to obtain defect causes; establishing a matching relationship between the defect causes and equipment attributes according to the defect causes; analyzing associated equipment according to the matching relationship to obtain predicted defect information of the associated equipment. Collecting defect data of abnormal equipment and analyzing to obtain defect causes can correctly judge the status of the equipment and prevent misjudgment; establishing a matching relationship between the defect causes and equipment attributes according to the defect causes can match the defect information of a single abnormal equipment with specific equipment attributes, improve the understanding of the equipment status, and facilitate subsequent analysis of other equipment; analyzing associated equipment according to the matching relationship to obtain predicted defect information of the associated equipment can improve the fault prediction capability of the entire equipment and reduce operation risks.

Description

Technical Field

[0001] The present invention belongs to the field of equipment management, and in particular relates to an equipment defect prediction method and system. Background Art

[0002] Industrial facilities include a lot of equipment, especially some large industrial facilities, which not only have a large number of equipment but also have very different types and distribution of equipment. The performance of equipment can affect the operation of industrial systems, so it is necessary to ensure that the selected equipment can meet the needs of the work.

[0003] Industrial facilities generally use similar equipment to reduce hardware and maintenance costs, so that they can be replaced when problems occur, while also reducing the training costs of maintenance personnel. However, if a problem occurs with a device, the risk of the same problem occurring in other devices must be eliminated.

[0004] In addition, the equipment is provided by the corresponding supplier. According to legal requirements, the supplier needs to guarantee the specifications of the equipment and ensure the stability of the equipment under reasonable conditions. If the supplier is unqualified, it will cause efficiency loss to industrial facilities and even safety hazards; therefore, ensuring the safety of equipment suppliers is the key to reducing the risk of large-scale accidents. Summary of the invention

[0005] In order to solve or improve the above problems, the present invention provides a method and system for predicting equipment defects. The specific technical solutions are as follows:

[0006] The present invention provides a method for predicting equipment defects, comprising: collecting defect data of abnormal equipment and analyzing to obtain defect causes; establishing a matching relationship between the defect causes and equipment attributes according to the defect causes; analyzing associated equipment according to the matching relationship to obtain predicted defect information of the associated equipment.

[0007] Preferably, the defect causes include process parameters, environmental parameters and structural parameters; the equipment attributes include functional parameters, structural attributes and manufacturer attributes.

[0008] Preferably, the associated device is of the same model or type as the abnormal device or a device of the same supplier; correspondingly, parsing the associated device according to the matching relationship to obtain predicted defect information of the associated device includes: obtaining abnormal prediction information according to the defect cause; obtaining the predicted defect information according to the type of association between the associated device and the abnormal device and the abnormal prediction information.

[0009] Preferably, the defect data belongs to the historical working parameters of the abnormal equipment; correspondingly, obtaining the abnormal prediction information according to the defect cause includes: setting a curve model based on the changes in the historical working parameters, and determining the abnormal prediction information according to the time when the defect data was generated.

[0010] Preferably, obtaining the predicted defect information based on the association type between the associated device and the abnormal device and the abnormal prediction information includes: selecting a corresponding correction value according to the association type, and modifying the abnormal time and abnormal type corresponding to the abnormal prediction information by the correction value to obtain the predicted defect information.

[0011] The present invention provides an equipment defect prediction system, comprising: a first unit, used to collect defect data of abnormal equipment and analyze it to obtain the cause of the defect; a second unit, used to establish a matching relationship between the defect cause and the equipment attribute according to the defect cause; and a third unit, used to analyze associated equipment according to the matching relationship to obtain predicted defect information of the associated equipment.

[0012] Preferably, the defect causes include process parameters, environmental parameters and structural parameters; the equipment attributes include functional parameters, structural attributes and manufacturer attributes.

[0013] Preferably, the associated device is of the same model or type as the abnormal device or a device of the same supplier; correspondingly, parsing the associated device according to the matching relationship to obtain predicted defect information of the associated device includes: obtaining abnormal prediction information according to the defect cause; obtaining the predicted defect information according to the type of association between the associated device and the abnormal device and the abnormal prediction information.

[0014] Preferably, the defect data belongs to the historical working parameters of the abnormal equipment; correspondingly, obtaining the abnormal prediction information according to the defect cause includes: setting a curve model based on the changes in the historical working parameters, and determining the abnormal prediction information according to the time when the defect data was generated.

[0015] Preferably, obtaining the predicted defect information based on the association type between the associated device and the abnormal device and the abnormal prediction information includes: selecting a corresponding correction value according to the association type, and modifying the abnormal time and abnormal type corresponding to the abnormal prediction information by the correction value to obtain the predicted defect information.

[0016] The beneficial effects of the present invention are as follows: by collecting defect data of abnormal equipment and analyzing the defect cause, the status of the equipment can be correctly judged to prevent misjudgment; by establishing a matching relationship between the defect cause and the equipment attribute, the defect information of a single abnormal equipment can be matched with specific equipment attributes, thereby improving the understanding of the equipment status and facilitating subsequent analysis of other equipment; by analyzing related equipment according to the matching relationship and obtaining the predicted defect information of the related equipment, the fault prediction capability of the entire equipment can be improved and the operation risk can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of a device defect prediction method according to the present invention;

[0018] Figure 2 is a schematic diagram of a device defect prediction system according to the present invention.

[0019] Description of main reference numerals:

[0020] 1-first unit, 2-second unit, 3-third unit. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0024] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] In order to solve or improve the problems raised in the background, the present invention provides Figure 1The device defect prediction method shown includes: S1, collecting defect data of abnormal equipment and analyzing to obtain the cause of the defect; S2, establishing a matching relationship between the defect cause and the device attribute; S3, analyzing the associated equipment according to the matching relationship to obtain the predicted defect information of the associated equipment.

[0026] Abnormality is used to describe the state of the equipment, that is, the working parameters or output results of the equipment do not meet the specifications of the equipment. The data when the working parameters or output results of the equipment do not meet the specifications of the equipment is defective data; taking the defective data as the cause and the abnormal phenomenon of the equipment as the result, analyzing their correlation to obtain the cause of the defective data that caused the abnormal phenomenon can correctly judge the state of the equipment and prevent misjudgment.

[0027] Equipment is a combination of engineering structure and circuit control. The functions of the equipment need to be realized with the help of engineering structure and circuit control, and cannot be realized by a single component alone. Therefore, the state of the engineering structure and circuit itself and the coordination between the two will affect the normal operation of the equipment; specifically, the state of different components themselves and the coordination between them will cause equipment abnormalities. Establishing a matching relationship with the equipment attributes based on the cause of the defect can clarify which component of the equipment or between components has a problem. Equipment attributes are used to describe the components, connection relationships, functional relationships and other external attributes of the equipment.

[0028] Industrial facilities generally have a large number of equipment, which may have anomalies similar to those of abnormal equipment or be affected by abnormal equipment and also become abnormal. Based on the structural similarity between the abnormal equipment and other equipment, or the degree of process correlation between the abnormal equipment and other equipment, the scope and degree of mutual influence between the two can be known. By analyzing the associated equipment according to the scope and degree, the predicted defect information of the associated equipment is obtained, and the defect information of a single abnormal equipment can be matched with specific equipment attributes, which improves the understanding of the equipment status and facilitates the subsequent analysis of other equipment.

[0029] The defect causes include process parameters, environmental parameters and structural parameters; the equipment attributes include functional parameters, structural attributes and manufacturer attributes.

[0030] Process parameters are not the data of the equipment itself, but the parameters that control the equipment when it is working. They are used to describe the working parameters and output data of the equipment under working conditions. The same equipment plays different roles in different industrial facilities, and the corresponding process parameters are different, which has different impacts on the equipment itself. The process parameters can be used to determine whether the equipment is suitable for working in this facility.

[0031] Environmental parameters are not the data of the device itself, but the data describing the working location of the device and the energy required for the device to work; the same device has different efficiencies in different working environments. For example, some devices require a low temperature environment and will fail in a high temperature environment, or require electricity higher than 220V to work properly, otherwise the output efficiency will be reduced. Environmental parameters can be used to determine whether the device is suitable for working in the current environment.

[0032] Structural parameters are the hardware attributes of the device itself, used to describe details such as what problems occur in the structure and circuit. Functional parameters are the software attributes of the device itself, used to describe the functions of the device. Structural attributes are the design attributes of the device itself, used to describe the design of its structure and circuit. Manufacturer attributes are external attributes of the device, used to describe the supplier of the device, including the manufacturer and seller.

[0033] By recording and analyzing the causes of defects including process parameters, environmental parameters and structural parameters; equipment attributes including functional parameters, structural attributes and manufacturer attributes, the status of other equipment with similar attributes can be reasonably inferred.

[0034] The associated device is a device of the same model or type or the same supplier as the abnormal device; correspondingly, parsing the associated device according to the matching relationship to obtain predicted defect information of the associated device includes: obtaining abnormal prediction information according to the defect cause; obtaining the predicted defect information according to the association type between the associated device and the abnormal device and the abnormal prediction information.

[0035] The manufacturing of equipment is standard, so if there is a problem, it may be because of potential defects (for the same model). Or it may be because of environmental parameters that cause equipment abnormality. Because the principles of equipment with similar functions (i.e. the same type) are generally not too different, they are similarly sensitive to the environment and have similar problems. In reality, some unscrupulous vendors will sell defective products, which may be a batch of defective products or defective products mixed with good products. In order to reduce risks, the entire batch of equipment needs to be monitored to prevent accidents.

[0036] Specifically, based on the cause of the defect, the abnormal prediction information of the abnormal device is obtained. At this time, the abnormal prediction information is not to predict the abnormality of the abnormal device again. Instead, it is based on the historical data of the abnormal device, taking a certain time point when the abnormal device is still normal as the starting point, and predicting how long it will take for the device to become abnormal. Because the device still appears to be in a normal state before the abnormality, the abnormal prediction information can be used to judge the experience provided by other devices.

[0037] The predicted defect information is obtained according to the type of association between the associated device and the abnormal device and the abnormal prediction information. The principle is that the higher the degree of association with the abnormal device, the greater the possibility of the same problem; correspondingly, the change of its working parameters is similar to or consistent with the change of the historical data of the abnormal device.

[0038] The defect data belongs to the historical working parameters of the abnormal equipment; correspondingly, obtaining the abnormal prediction information according to the defect cause includes: setting a curve model based on the changes in the historical working parameters, and determining the abnormal prediction information according to the time when the defect data was generated.

[0039] Before an abnormal device becomes abnormal, it behaves like a normal device. Therefore, its related working parameters, i.e., historical working data, will include normal working data, some abnormal working data, and abnormal working data. Among them, some abnormal working data and abnormal working data are defect data. A curve model is set according to the changes in historical working parameters, and then the abnormal prediction information can be determined according to the time when the corresponding data was generated.

[0040] The method of obtaining the predicted defect information based on the association type between the associated device and the abnormal device and the abnormal prediction information includes: selecting a corresponding correction value according to the association type, and modifying the abnormal time and abnormal type corresponding to the abnormal prediction information by the correction value to obtain the predicted defect information.

[0041] The types of association include: same model, same type and same supplier. Among them, if a problem occurs with the same model of equipment in the same industrial facility, then the possibility of problems with other equipment of the same model is the same, and special attention should be paid. The change in the corresponding working data is very likely to be similar to the working data of the abnormal equipment, and the time of the abnormality will be relatively close. The corresponding correction value can be very small, which can be hours, and the corresponding abnormality type is also the same. The possibility of abnormality of the same type of equipment is lower, and the corresponding correction value can be several days, weeks and months, and the corresponding abnormality type is also similar. The situation with the same supplier is more complicated and can be set according to the actual situation.

[0042] The present invention provides Figure 2 The device defect prediction system shown includes: a first unit 1, used to collect defect data of abnormal equipment and analyze it to obtain the cause of the defect; a second unit 2, used to establish a matching relationship between the defect cause and the device attribute according to the defect cause; a third unit 3, used to analyze the associated equipment according to the matching relationship to obtain the predicted defect information of the associated equipment.

[0043] The defect causes include process parameters, environmental parameters and structural parameters; the equipment attributes include functional parameters, structural attributes and manufacturer attributes.

[0044] The associated device is a device of the same model or type or the same supplier as the abnormal device; correspondingly, parsing the associated device according to the matching relationship to obtain predicted defect information of the associated device includes: obtaining abnormal prediction information according to the defect cause; obtaining the predicted defect information according to the association type between the associated device and the abnormal device and the abnormal prediction information.

[0045] The defect data belongs to the historical working parameters of the abnormal equipment; correspondingly, obtaining the abnormal prediction information according to the defect cause includes: setting a curve model based on the changes in the historical working parameters, and determining the abnormal prediction information according to the time when the defect data was generated.

[0046] The method of obtaining the predicted defect information based on the association type between the associated device and the abnormal device and the abnormal prediction information includes: selecting a corresponding correction value according to the association type, and modifying the abnormal time and abnormal type corresponding to the abnormal prediction information by the correction value to obtain the predicted defect information.

[0047] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed in this embodiment can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0048] In the embodiments provided in the present application, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units may be combined into one unit, one unit may be split into multiple units, or some features may be ignored.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for predicting equipment defects, characterized in that: include: Collect defect data of abnormal equipment and analyze the causes of defects; The defect data belongs to the historical working parameters of the abnormal equipment; the defect causes include process parameters, environmental parameters and structural parameters; the process parameters are parameters for controlling the operation of the equipment, and are used to describe the working parameters and output data of the equipment under the working state; The structural parameters are the hardware properties of the device itself; A matching relationship is established between the defect cause and the device attributes; the device attributes include functional parameters, structural attributes and manufacturer attributes; the functional parameters are the software attributes of the device itself, which are used to describe the functions of the device; the structural attributes are the design attributes of the device itself, which are used to describe the structure and circuit design of the device; Analyze the associated devices according to the matching relationship to obtain predicted defect information of the associated devices; The associated device is a device of the same model or type as the abnormal device or a device of the same supplier; Correspondingly, parsing the associated devices according to the matching relationship to obtain predicted defect information of the associated devices includes: According to the defect cause, abnormal prediction information is obtained, including: Setting a curve model based on changes in the historical working parameters, and determining the abnormality prediction information according to the time when the defect data was generated; The predicted defect information is obtained according to the association type between the associated device and the abnormal device and the abnormal prediction information, specifically including: A corresponding correction value is selected according to the association type, and the abnormal time and abnormal type corresponding to the abnormal prediction information are modified by the correction value to obtain the predicted defect information.

2. A device defect prediction system, characterized in that: include: The first unit is used to collect defect data of abnormal equipment and analyze the cause of the defect; The defect data belongs to the historical operating parameters of the abnormal device; The defect causes include process parameters, environmental parameters and structural parameters; the process parameters are parameters for controlling the operation of the equipment and are used to describe the working parameters and output data of the equipment under the working state; The structural parameters are the hardware properties of the device itself; The second unit is used to establish a matching relationship between the defect cause and the device attribute; the device attribute includes function parameters, structure attributes and manufacturer attributes; the function parameters are the software attributes of the device itself, which are used to describe the functions of the device; the structure attributes are the design attributes of the device itself, which are used to describe the structure and circuit design of the device; A third unit is used to analyze the associated device according to the matching relationship to obtain predicted defect information of the associated device; The associated device is a device of the same model or type as the abnormal device or a device of the same supplier; Correspondingly, parsing the associated devices according to the matching relationship to obtain predicted defect information of the associated devices includes: According to the defect cause, abnormal prediction information is obtained, including: Setting a curve model based on changes in the historical working parameters, and determining the abnormality prediction information according to the time when the defect data was generated; The predicted defect information is obtained according to the association type between the associated device and the abnormal device and the abnormal prediction information, specifically including: A corresponding correction value is selected according to the association type, and the abnormal time and abnormal type corresponding to the abnormal prediction information are modified by the correction value to obtain the predicted defect information.

Images